中文
相关论文

相关论文: Representation of 2D frame less visual space as a …

200 篇论文

In machine learning, data is usually represented in a (flat) Euclidean space where distances between points are along straight lines. Researchers have recently considered more exotic (non-Euclidean) Riemannian manifolds such as hyperbolic…

机器学习 · 计算机科学 2021-01-12 Marc T. Law , Jos Stam

Hyperbolic geometry, a Riemannian manifold endowed with constant sectional negative curvature, has been considered an alternative embedding space in many learning scenarios, \eg, natural language processing, graph learning, \etc, as a…

计算机视觉与模式识别 · 计算机科学 2023-04-24 Pengfei Fang , Mehrtash Harandi , Trung Le , Dinh Phung

The present paper aims to develop a mathematical model concerning the visual perception of spatial information. It is a challenging problem in theoretical neuroscience to investigate how the spatial information of the objects in the…

神经元与认知 · 定量生物学 2025-05-21 Debasis Mazumdar , Kuntal Ghosh , Soma Mitra , Late Kamales Bhaumik

Deep representation learning is a ubiquitous part of modern computer vision. While Euclidean space has been the de facto standard manifold for learning visual representations, hyperbolic space has recently gained rapid traction for learning…

计算机视觉与模式识别 · 计算机科学 2023-05-12 Pascal Mettes , Mina Ghadimi Atigh , Martin Keller-Ressel , Jeffrey Gu , Serena Yeung

Geometric representation learning has recently shown great promise in several machine learning settings, ranging from relational learning to language processing and generative models. In this work, we consider the problem of performing…

机器学习 · 统计学 2020-05-29 Gian Maria Marconi , Lorenzo Rosasco , Carlo Ciliberto

Hyperbolic geometry has recently found applications in social networks, machine learning and computational biology. With the increasing popularity, questions about the best representations of hyperbolic spaces arise, as each representation…

数值分析 · 数学 2024-04-16 Dorota Celinska-Kopczynska , Eryk Kopczynski

Hyperbolic spaces have recently gained momentum in the context of machine learning due to their high capacity and tree-likeliness properties. However, the representational power of hyperbolic geometry is not yet on par with Euclidean…

机器学习 · 计算机科学 2018-06-29 Octavian-Eugen Ganea , Gary Bécigneul , Thomas Hofmann

Understanding the intricate mappings between visual stimuli and neural responses is a fundamental challenge in cognitive neuroscience. While current approaches predominantly align images and functional magnetic resonance imaging (fMRI)…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Zihan Ma , Tian Xia , Kexin Wang , Xiao Li , Xiaowei He , Yudan Ren

In this paper, we present a method of embedding physics data manifolds with metric structure into lower dimensional spaces with simpler metrics, such as Euclidean and Hyperbolic spaces. We then demonstrate that it can be a powerful step in…

高能物理 - 唯象学 · 物理学 2023-08-02 Sang Eon Park , Philip Harris , Bryan Ostdiek

Learning low-dimensional numerical representations from symbolic data, e.g., embedding the nodes of a graph into a geometric space, is an important concept in machine learning. While embedding into Euclidean space is common, recent…

机器学习 · 计算机科学 2024-10-10 Thomas Bläsius , Jean-Pierre von der Heydt , Maximilian Katzmann , Nikolai Maas

Hyperbolic neural networks have been popular in the recent past due to their ability to represent hierarchical data sets effectively and efficiently. The challenge in developing these networks lies in the nonlinearity of the embedding space…

机器学习 · 计算机科学 2021-12-08 Xiran Fan , Chun-Hao Yang , Baba C. Vemuri

Recent research has shown that alignment between the structure of graph data and the geometry of an embedding space is crucial for learning high-quality representations of the data. The uniform geometry of Euclidean and hyperbolic spaces…

机器学习 · 计算机科学 2023-06-27 Wei Zhao , Federico Lopez , J. Maxwell Riestenberg , Michael Strube , Diaaeldin Taha , Steve Trettel

Graph-structured data are widespread in real-world applications, such as social networks, recommender systems, knowledge graphs, chemical molecules etc. Despite the success of Euclidean space for graph-related learning tasks, its ability to…

机器学习 · 计算机科学 2022-11-09 Min Zhou , Menglin Yang , Lujia Pan , Irwin King

Higher-dimensional spaces are ubiquitous in applications of mathematics. Yet, as we live in a three-dimensional space, visualizing, say, a four-dimensional space is challenging. We introduce a novel method of interactive visualization of…

图形学 · 计算机科学 2021-10-04 Eryk Kopczyński , Dorota Celińska-Kopczyńska

Multidimensional scaling (MDS) is a widely used approach to representing high-dimensional, dependent data. MDS works by assigning each observation a location on a low-dimensional geometric manifold, with distance on the manifold…

统计方法学 · 统计学 2023-08-16 Bolun Liu , Shane Lubold , Adrian E. Raftery , Tyler H. McCormick

Recent progress in artificial intelligence has encouraged numerous attempts to understand and decode human visual system from brain signals. These prior works typically align neural activity independently with semantic and perceptual…

人工智能 · 计算机科学 2026-03-25 Sangmin Jo , Wootaek Jeong , Da-Woon Heo , Yoohwan Hwang , Heung-Il Suk

Hyperdimensional (HD) computing is a set of neurally inspired methods for obtaining high-dimensional, low-precision, distributed representations of data. These representations can be combined with simple, neurally plausible algorithms to…

机器学习 · 计算机科学 2022-02-21 Anthony Thomas , Sanjoy Dasgupta , Tajana Rosing

Learning from graph-structured data is an important task in machine learning and artificial intelligence, for which Graph Neural Networks (GNNs) have shown great promise. Motivated by recent advances in geometric representation learning, we…

机器学习 · 计算机科学 2019-10-30 Qi Liu , Maximilian Nickel , Douwe Kiela

High-dimensional multiplex graphs are characterized by their high number of complementary and divergent dimensions. The existence of multiple hierarchical latent relations between the graph dimensions poses significant challenges to…

机器学习 · 计算机科学 2025-01-30 Kamel Abdous , Nairouz Mrabah , Mohamed Bouguessa

This paper introduces a method of calculating and rendering shapes in a non-Euclidean 2D space. In order to achieve this, we developed a physics and graphics engine that uses hyperbolic trigonometry to calculate and subsequently render the…

图形学 · 计算机科学 2019-08-13 Daniil Osudin , Christopher Child , Yang-Hui He
‹ 上一页 1 2 3 10 下一页 ›